{"id":"https://openalex.org/W4308824155","doi":"https://doi.org/10.1109/sdf55338.2022.9931697","title":"Audio-Visual Active Speaker Identification: A comparison of dense image-based features and sparse facial landmark-based features","display_name":"Audio-Visual Active Speaker Identification: A comparison of dense image-based features and sparse facial landmark-based features","publication_year":2022,"publication_date":"2022-10-12","ids":{"openalex":"https://openalex.org/W4308824155","doi":"https://doi.org/10.1109/sdf55338.2022.9931697"},"language":"en","primary_location":{"id":"doi:10.1109/sdf55338.2022.9931697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sdf55338.2022.9931697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Sensor Data Fusion: Trends, Solutions, Applications (SDF)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://biblio.ugent.be/publication/01GJQ3JQ8ZY54K5MBDV6TZFBEY/file/01GJQ3N2DMAKFTZV4JRWFA9RGK.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068725183","display_name":"Warre Geeroms","orcid":"https://orcid.org/0000-0002-2904-1987"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Warre Geeroms","raw_affiliation_strings":["Ghent University - imec,TELIN-IPI,Belgium","IDLab-ELIS, Ghent University - imec, Belgium","TELIN-IPI, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,TELIN-IPI,Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I4210114974"]},{"raw_affiliation_string":"IDLab-ELIS, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]},{"raw_affiliation_string":"TELIN-IPI, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074485158","display_name":"Gianni Allebosch","orcid":"https://orcid.org/0000-0003-2502-3746"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Gianni Allebosch","raw_affiliation_strings":["Ghent University - imec,TELIN-IPI,Belgium","TELIN-IPI, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,TELIN-IPI,Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I4210114974"]},{"raw_affiliation_string":"TELIN-IPI, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012036252","display_name":"Stijn Kindt","orcid":"https://orcid.org/0000-0001-9300-4251"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Stijn Kindt","raw_affiliation_strings":["Ghent University - imec,IDLab-ELIS,Belgium","IDLab-ELIS, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab-ELIS,Belgium","institution_ids":["https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab-ELIS, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016655961","display_name":"Loubna Kadri","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Loubna Kadri","raw_affiliation_strings":["Ghent University - imec,IDLab-ELIS,Belgium","IDLab-ELIS, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab-ELIS,Belgium","institution_ids":["https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab-ELIS, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068050252","display_name":"Peter Veelaert","orcid":"https://orcid.org/0000-0003-4746-9087"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]},{"id":"https://openalex.org/I4210114974","display_name":"IMEC","ror":"https://ror.org/02kcbn207","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I4210114974"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Peter Veelaert","raw_affiliation_strings":["Ghent University - imec,TELIN-IPI,Belgium","TELIN-IPI, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,TELIN-IPI,Belgium","institution_ids":["https://openalex.org/I39327780","https://openalex.org/I4210114974"]},{"raw_affiliation_string":"TELIN-IPI, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]},{"id":"https://openalex.org/I39327780","display_name":"iMinds","ror":"https://ror.org/03baec336","country_code":"BE","type":"nonprofit","lineage":["https://openalex.org/I39327780"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["Ghent University - imec,IDLab-ELIS,Belgium","IDLab-ELIS, Ghent University - imec, Belgium"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ghent University - imec,IDLab-ELIS,Belgium","institution_ids":["https://openalex.org/I39327780"]},{"raw_affiliation_string":"IDLab-ELIS, Ghent University - imec, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3689,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52257088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8463066220283508},{"id":"https://openalex.org/keywords/landmark","display_name":"Landmark","score":0.8396929502487183},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7406133413314819},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.532166600227356},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5147966742515564},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5117027759552002},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5033525824546814},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.500312089920044},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.48667341470718384},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.43824559450149536},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.43266773223876953},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.43154630064964294},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.41465532779693604},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.35691213607788086},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.10067310929298401}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8463066220283508},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.8396929502487183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7406133413314819},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.532166600227356},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5147966742515564},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5117027759552002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5033525824546814},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.500312089920044},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.48667341470718384},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43824559450149536},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.43266773223876953},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.43154630064964294},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.41465532779693604},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.35691213607788086},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.10067310929298401},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/sdf55338.2022.9931697","is_oa":false,"landing_page_url":"https://doi.org/10.1109/sdf55338.2022.9931697","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Sensor Data Fusion: Trends, Solutions, Applications (SDF)","raw_type":"proceedings-article"},{"id":"pmh:oai:archive.ugent.be:01GJQ3JQ8ZY54K5MBDV6TZFBEY","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01GJQ3JQ8ZY54K5MBDV6TZFBEY","pdf_url":"https://biblio.ugent.be/publication/01GJQ3JQ8ZY54K5MBDV6TZFBEY/file/01GJQ3N2DMAKFTZV4JRWFA9RGK.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781665486729","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:archive.ugent.be:01GJQ3JQ8ZY54K5MBDV6TZFBEY","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01GJQ3JQ8ZY54K5MBDV6TZFBEY","pdf_url":"https://biblio.ugent.be/publication/01GJQ3JQ8ZY54K5MBDV6TZFBEY/file/01GJQ3N2DMAKFTZV4JRWFA9RGK.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISBN: 9781665486729","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.6200000047683716,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4308824155.pdf","grobid_xml":"https://content.openalex.org/works/W4308824155.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1549884461","https://openalex.org/W2098597588","https://openalex.org/W2154636774","https://openalex.org/W2330149154","https://openalex.org/W2604379605","https://openalex.org/W2807126412","https://openalex.org/W2808631503","https://openalex.org/W2885905848","https://openalex.org/W2891205112","https://openalex.org/W2954458766","https://openalex.org/W2963307811","https://openalex.org/W2964015378","https://openalex.org/W3206008172","https://openalex.org/W4288282320","https://openalex.org/W6674693820","https://openalex.org/W6726873649","https://openalex.org/W6735927292","https://openalex.org/W6743555153","https://openalex.org/W6752581720","https://openalex.org/W6754420807","https://openalex.org/W6765865358"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W3004352674","https://openalex.org/W1975359510","https://openalex.org/W3110605476","https://openalex.org/W1803351015","https://openalex.org/W2363106653"],"abstract_inverted_index":{"The":[0,136],"field":[1],"of":[2,20,40,80,163,178,183,213],"speaker":[3,96,215],"detection":[4],"is":[5,54,106,149,166,174,196],"relatively":[6],"well":[7],"researched.":[8],"Multiple":[9],"solutions":[10],"focusing":[11],"solely":[12],"on":[13,101],"audio":[14,25,42],"or":[15,17,181],"video,":[16],"a":[18,27,37,64,67,122,143,150,168,175,197,210],"combination":[19],"both":[21,100],"exist.":[22],"On":[23,44],"the":[24,41,45,83,109,118,128,131,161,187],"side,":[26,47],"popular":[28],"feature":[29,70,189],"representation":[30,39],"are":[31,36,51],"mel-frequency":[32],"cepstral":[33],"coefficients,":[34],"which":[35,53],"sparse":[38,56,68],"signal.":[43],"video":[46,69],"mostly":[48],"pixel":[49,132],"intensities":[50],"used,":[52],"not":[55],"at":[57,66],"all.":[58],"In":[59],"this":[60,195],"paper,":[61],"we":[62,87,120,202],"take":[63],"look":[65],"representation,":[71],"namely":[72],"facial":[73,115],"landmarks.":[74,116],"We":[75],"first":[76],"evaluate":[77],"what":[78],"selection":[79],"landmarks":[81],"conveys":[82],"most":[84],"information.":[85],"Afterwards":[86],"propose":[88],"several":[89],"neural":[90],"network":[91],"architectures":[92,113],"trained":[93],"for":[94,142,155],"audio-visual":[95],"detection.":[97],"A":[98],"comparison":[99],"computational":[102,170],"performance":[103,154],"and":[104,112,133,159,207],"accuracy":[105],"shown":[107],"between":[108,130],"original":[110],"architecture":[111],"utilizing":[114],"For":[117],"evaluation,":[119],"introduce":[121],"new":[123],"dataset":[124],"to":[125,186,204],"better":[126],"understand":[127],"differences":[129],"landmark":[134,137],"features.":[135],"features":[138],"achieve":[139],"similar":[140],"accuracies":[141],"forward":[144],"oriented":[145],"head":[146,157],"position.":[147],"There":[148,165],"small":[151],"reduction":[152,177],"in":[153,160,209],"non-ideal":[156],"positions":[158],"case":[162],"occlusions.":[164],"however":[167],"significant":[169],"benefit,":[171],"as":[172],"there":[173],"complexity":[176],"orders":[179],"two":[180],"three":[182],"magnitude":[184],"due":[185],"decreased":[188],"dimensionality.":[190],"When":[191],"considering":[192],"embedded":[193],"devices,":[194],"big":[198],"upside.":[199],"This":[200],"way":[201],"hope":[203],"provide":[205],"insight":[206],"interest":[208],"novel":[211],"type":[212],"active":[214],"identification":[216],"models.":[217]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}